Sidechat logo
Download TikTok Instagram X
Sidechat icon
Join communities on Sidechat Download
US Politics icon
US Politics 5w
Statistics Lesson for US Politics Idiots #1: a random sample size of 300, 500, 1000, or 2000 people is mathematically good enough to make wide ranging claims about a population. You don’t need 300 million people. Stop claiming that excuse please.
comment

4
upvote 3 downvote
default user profile icon
Anonymous 5w

Depends on the claim and the sampling methods.

upvote 3 downvote
default user profile icon
Anonymous 5w

I’ve seen people make this dumbass claim dozens of times and I’m tired of it :(

upvote 1 downvote
default user profile icon
Anonymous replying to -> #1 5w

That is why I said RANDOM SAMPLE. That is a term that can be defined in statistics. Also It usually does not depend on the claim although certain spaces (MEDICINE, NOT POLI SCI) may have higher sample sizes required for obvious rigor.

upvote 1 downvote
default user profile icon
Anonymous replying to -> OP 5w

The problem is it’s nearly impossible to get a completely random sample. Any survey method is going to carry with it some level of sampling bias. People have been pulling out the “2.5 million gun self defense per year” thing for decades and it was based on one faulty study. Most people don’t know what good sampling is.

upvote 5 downvote